相关论文: Task Arithmetic in Trust Region: A Training-Free M…

While most current approaches rely on further training techniques, such as fine-tuning or reinforcement learning, to enhance model capacities, model merging stands out for its ability of improving models without requiring any additional…

Adapting pre-trained models with broad capabilities has become standard practice for learning a wide range of downstream tasks. The typical approach of fine-tuning different models for each task is performant, but incurs a substantial…

In recent times Large Language Models have exhibited tremendous capabilities, especially in the areas of mathematics, code generation and general-purpose reasoning. However for specialized domains especially in applications that require…

Model merging seeks to integrate task-specific expert models into a unified architecture while preserving multi-task generalization capabilities, yet parameter interference between constituent models frequently induces performance…

Integrating Automatic Speech Recognition (ASR) into Speech Emotion Recognition (SER) enhances modeling by providing linguistic context. However, conventional feature fusion faces performance bottlenecks, and multi-task learning often…

Task arithmetic is a straightforward yet highly effective strategy for model merging, enabling the resultant model to exhibit multi-task capabilities. Recent research indicates that models demonstrating linearity enhance the performance of…

Sharpness-aware minimization (SAM) reports improving domain generalization by reducing the loss surface curvature in the parameter space. However, generalization during fine-tuning is often more dependent on the transferability of…

Multitask learning is a widely used paradigm for training models on diverse tasks, with applications ranging from graph neural networks to language model fine-tuning. Since tasks may interfere with each other, a key notion for modeling…

Multi-task learning (MTL) concurrently trains a model on diverse task datasets to exploit common features, thereby improving overall performance across the tasks. Recent studies have dedicated efforts to merging multiple independent model…

The advent of large language models (LLMs) like GPT-4 has catalyzed the exploration of multi-task learning (MTL), in which a single model demonstrates proficiency across diverse tasks. Task arithmetic has emerged as a cost-effective…

Deep learning models have demonstrated exceptional performance across a wide range of computer vision tasks. However, their performance often degrades significantly when faced with distribution shifts, such as domain or dataset changes.…

Task arithmetic, representing downstream tasks through linear operations on task vectors, has emerged as a simple yet powerful paradigm for transferring knowledge across diverse settings. However, maintaining a large collection of task…

Task arithmetic has emerged as a promising approach for editing models by representing task-specific knowledge as composable task vectors. However, existing methods rely on network linearization to derive task vectors, leading to…

Model merging combines fine-tuned checkpoints into a single multi-task model without retraining. Existing methods - such as task arithmetic, model soups, TIES, and DARE - are computationally efficient and empirically successful, but rely on…

Tabular data have been playing a mostly important role in diverse real-world fields, such as healthcare, engineering, finance, etc. The recent success of deep learning has fostered many deep networks (e.g., Transformer, ResNet) based…

Large language models increasingly rely on either reinforcement learning or multi-agent prompting to improve reasoning, yet these two paradigms remain difficult to combine. Directly applying single-agent reinforcement learning to multi-turn…

Model merging has shown that multitask models can be created by directly combining the parameters of different models that are each specialized on tasks of interest. However, models trained independently on distinct tasks often exhibit…

There is a recent proliferation of research on the integration of machine learning and optimization. One expansive area within this research stream is predictive-model embedded optimization, which proposes the use of pre-trained predictive…

Multi-task learning (MTL) aims to leverage shared information among tasks to improve learning efficiency and accuracy. However, MTL often struggles to effectively manage positive and negative transfer between tasks, which can hinder…

Adapting models pre-trained on large-scale datasets is a proven way to reach strong performance quickly for down-stream tasks. However, the growth of state-of-the-art mod-els makes traditional full fine-tuning unsuitable and difficult,…